Web search activity data accurately predict population chronic disease risk in the USA Nguyen, Thin, Tran, Truyen, Luo, Wei, Gupta, Sunil, Rana, Santu, Phung, Dinh, Nichols, Melanie, Millar, Lynne, Venkatesh, Svetha and Allender, Steve 2015, Web search activity data accurately predict population chronic disease risk in the USA, Journal of epidemiology and community health, vol. 69, no. 7, pp. 693-699, doi: 10.1136/jech-2014-204523. Attached Files Name Description MIMEType Size Downloads Title Web search activity data accurately predict population chronic disease risk in the USA Author(s) Nguyen, Thin orcid.org/0000-0003-3467-8963 Tran, Truyen orcid.org/0000-0001-6531-8907 Luo, Wei orcid.org/0000-0002-4711-7543 Gupta, Sunil orcid.org/0000-0002-3308-1930 Rana, Santu orcid.org/0000-0003-2247-850X Phung, Dinh orcid.org/0000-0002-9977-8247 Nichols, Melanie orcid.org/0000-0002-7834-5899 Millar, Lynne Venkatesh, Svetha orcid.org/0000-0001-8675-6631 Allender, Steve orcid.org/0000-0002-4842-3294 Journal name Journal of epidemiology and community health Volume number 69 Issue number 7 Start page 693 End page 699 Total pages 7 Publisher BMJ Publishing Group Place of publication London, Eng. Publication date 2015 ISSN 1470-2738 Keyword(s) EPIDEMIOLOGY HEALTH BEHAVIOUR HEALTH PROMOTION SURVEILLANCE Science & Technology Life Sciences & Biomedicine Public, Environmental & Occupational Health PUBLIC-HEALTH GOOGLE TRENDS OBESITY MODELS Summary BACKGROUND: The WHO framework for non-communicable disease (NCD) describes risks and outcomes comprising the majority of the global burden of disease. These factors are complex and interact at biological, behavioural, environmental and policy levels presenting challenges for population monitoring and intervention evaluation. This paper explores the utility of machine learning methods applied to population-level web search activity behaviour as a proxy for chronic disease risk factors. METHODS: Web activity output for each element of the WHO's Causes of NCD framework was used as a basis for identifying relevant web search activity from 2004 to 2013 for the USA. Multiple linear regression models with regularisation were used to generate predictive algorithms, mapping web search activity to Centers for Disease Control and Prevention (CDC) measured risk factor/disease prevalence. Predictions for subsequent target years not included in the model derivation were tested against CDC data from population surveys using Pearson correlation and Spearman's r. RESULTS: For 2011 and 2012, predicted prevalence was very strongly correlated with measured risk data ranging from fruits and vegetables consumed (r=0.81; 95% CI 0.68 to 0.89) to alcohol consumption (r=0.96; 95% CI 0.93 to 0.98). Mean difference between predicted and measured differences by State ranged from 0.03 to 2.16. Spearman's r for state-wise predicted versus measured prevalence varied from 0.82 to 0.93. CONCLUSIONS: The high predictive validity of web search activity for NCD risk has potential to provide real-time information on population risk during policy implementation and other population-level NCD prevention efforts. Language eng DOI 10.1136/jech-2014-204523 Field of Research 080109 Pattern Recognition and Data Mining 111706 Epidemiology 111711 Health Information Systems (incl Surveillance) 110201 Cardiology (incl Cardiovascular Diseases) Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences HERDC Research category C1 Refereed article in a scholarly journal ERA Research output type C Journal article Copyright notice ©2015, BMJ Publishing Group Persistent URL http://hdl.handle.net/10536/DRO/DU:30074199 Document type: Journal Article Collections: Faculty of Health Faculty of Science, Engineering and Built Environment Population Health Centre for Pattern Recognition and Data Analytics (PRADA) Related Links Link Description Connect to published version Go to link with your DU access privileges     Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved. Versions Version Filter Type Thu, 09 Jul 2015, 12:23:29 EST Thu, 09 Jul 2015, 14:03:02 EST Thu, 09 Jul 2015, 14:14:16 EST Wed, 23 Sep 2015, 12:31:26 EST Mon, 18 Jan 2016, 07:28:02 EST Wed, 24 Feb 2016, 10:00:08 EST Wed, 24 Feb 2016, 10:03:31 EST Filtered Full Citation counts:   Cited 10 times in TR Web of Science Cited 11 times in Scopus Search Google Scholar Access Statistics: 644 Abstract Views, 3 File Downloads  -  Detailed Statistics Created: Wed, 23 Sep 2015, 12:31:26 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.